CN112307969A - Pulse signal classification identification method and device and computer equipment - Google Patents
Pulse signal classification identification method and device and computer equipment Download PDFInfo
- Publication number
- CN112307969A CN112307969A CN202011193883.4A CN202011193883A CN112307969A CN 112307969 A CN112307969 A CN 112307969A CN 202011193883 A CN202011193883 A CN 202011193883A CN 112307969 A CN112307969 A CN 112307969A
- Authority
- CN
- China
- Prior art keywords
- pulse
- signal
- clusters
- radio frequency
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 100
- 230000009467 reduction Effects 0.000 claims abstract description 73
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000005070 sampling Methods 0.000 claims description 35
- 238000001228 spectrum Methods 0.000 claims description 34
- 230000015654 memory Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 11
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000010183 spectrum analysis Methods 0.000 claims description 6
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 51
- 208000028659 discharge Diseases 0.000 description 58
- 230000036961 partial effect Effects 0.000 description 56
- 230000000875 corresponding effect Effects 0.000 description 19
- 238000001914 filtration Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 13
- 238000012544 monitoring process Methods 0.000 description 12
- 230000008878 coupling Effects 0.000 description 10
- 238000010168 coupling process Methods 0.000 description 10
- 238000005859 coupling reaction Methods 0.000 description 10
- 230000001360 synchronised effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000009413 insulation Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 230000004927 fusion Effects 0.000 description 7
- 230000002829 reductive effect Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 230000001629 suppression Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000704 physical effect Effects 0.000 description 4
- 230000004224 protection Effects 0.000 description 4
- 238000012935 Averaging Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000003750 conditioning effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 208000032365 Electromagnetic interference Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Abstract
The invention discloses a classification identification method and device of pulse signals and computer equipment, wherein the method comprises the following steps: acquiring target sample data of the radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; respectively generating a plurality of corresponding feature sets according to the target pulse cluster; and determining the type of the target pulse cluster according to the feature set. The radio frequency pulse signals are combined to be identified, extracted, clustered and grouped, reasonably denoised and classified, so that the pulse type signals are effectively inhibited, the accuracy of local discharge detection and signal source positioning is improved, and false alarms are avoided.
Description
Technical Field
The invention relates to the technical field of intelligent sensing and measurement for state monitoring of power equipment, in particular to a pulse signal classification identification method and device and computer equipment.
Background
Monitoring the health condition and the operation state of the power grid equipment is an important guarantee for guaranteeing the safe operation of the power grid. There are many kinds of insulation protection in the electric network equipment, and the insulation protection ages gradually under long-term mechanical, electrical, thermal, chemical action, and in the area of higher electric field intensity, the charge moves directionally at the position of weaker insulation, forming partial discharge but not breaking down the insulation. Partial discharges are therefore an early sign of possible failure of the grid equipment. It is also necessary to detect and locate the partial discharge signal.
In the related art, the method is mainly a method for detecting the partial discharge broadband radio frequency pulse based on spatial coupling, but for the partial discharge broadband radio frequency pulse signal in an open space, various electromagnetic interference signals are easily introduced, so that false alarm and false alarm of partial discharge detection are caused. Specifically, in a substation strong electromagnetic environment, electromagnetic interference signals are common, and there are periodic narrow-band interference (such as radio broadcasting, mobile communication carrier waves, and the like), pulse-type interference (such as corona discharge, random pulses generated by electromagnetic switch operation or power electronics), and white noise interference. Because the pulse-type interference and the partial discharge pulse signal have similar time-frequency characteristics, and the white noise interference covers the full frequency band of pulse detection and continuously exists in the time domain, the white noise interference is superposed on the partial discharge signal to reduce the signal-to-noise ratio of the partial discharge signal, so that the partial discharge signal and the interference signal are more similar in the time domain waveform, the interference signal and the partial discharge signal cannot be accurately distinguished based on waveform characteristics, errors and misjudgments of the partial discharge signal are caused, and the accuracy of the partial discharge detection is reduced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and a computer device for classifying and identifying a pulse signal, so as to solve the problem that reliability of partial discharge detection is reduced due to various electromagnetic interferences in an existing partial discharge signal detection process.
According to a first aspect, an embodiment of the present invention provides a method for classifying and identifying pulse signals, including: acquiring target sample data of a radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; respectively generating a plurality of corresponding feature sets according to the target pulse clusters; and determining the type of the target pulse cluster according to the feature set.
With reference to the first aspect, in a first implementation manner of the first aspect, the step of performing out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters specifically includes: carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters and positioning results thereof; and performing cluster optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the step of performing out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters specifically includes: performing spectrum analysis on the initial pulse cluster to determine an out-of-band noise reduction frequency band range of the initial pulse cluster; generating a second pulse cluster according to the out-of-band noise reduction frequency band range; determining the principal dimension of the second pulse cluster according to a preset principal component analysis algorithm; and generating a plurality of first pulse clusters in each second pulse cluster by reducing dimensions and denoising according to the main dimensions of the second pulse clusters.
With reference to the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the step of generating a positioning result of a plurality of first pulse clusters specifically includes: respectively acquiring signal intensity ratios and/or arrival time differences of a plurality of first pulse clusters reaching each sensor; and generating a positioning result of a plurality of first pulse clusters according to the signal strength ratio and/or the arrival time difference.
With reference to the third implementation manner of the first aspect, in the fourth implementation manner of the first aspect, the performing cluster optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters specifically includes: respectively determining the signal source positions of the first pulse clusters according to the positioning results of the first pulse clusters; when the signal source positions of the first pulse clusters are the same, the first pulse clusters are target pulse clusters; and/or when the signal source positions of the first pulse clusters are different, generating a plurality of sub-pulse clusters according to the signal source positions, wherein the sub-pulse clusters are target pulse clusters; and/or when the signal source positions of different first pulse clusters are the same, generating a super pulse cluster according to the signal source positions, wherein the super pulse cluster is a target pulse cluster;
with reference to the first aspect, in a fifth implementation manner of the first aspect, the acquiring target sample data of the radio frequency pulse signal specifically includes: acquiring a simulated radio frequency signal which accords with a target frequency band range and a target signal intensity range; acquiring the highest frequency of the analog radio frequency signal, and determining a sampling frequency according to the highest frequency; sampling the analog radio frequency signal according to the sampling frequency, the sampling vertical resolution and the sampling clock synchronization precision to generate sample data of the radio frequency signal; and extracting sample data which accords with the characteristics of a preset pulse signal from the sample data of the radio frequency signal, and generating target sample data of the radio frequency pulse signal.
With reference to the first aspect, in a sixth implementation manner of the first aspect, the performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal specifically includes: performing spectrum analysis on the target sample data to determine a frequency band range of the target sample data; and generating a first radio frequency pulse signal according to the frequency band range and the target sample data.
With reference to the first aspect, in a seventh implementation manner of the first aspect, the clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters specifically includes: dividing the first radio frequency pulse signal into a plurality of second radio frequency pulse signals according to the sensor identification information of the first radio frequency pulse signal; and respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio frequency pulse signals.
With reference to the seventh implementation manner of the first aspect, in the eighth implementation manner of the first aspect, the method further includes: calculating and generating a first coincidence ratio of each second radio-frequency pulse signal according to a plurality of initial pulse clusters corresponding to the second radio-frequency pulse signals; determining a first clustering grouping result of each second radio frequency pulse signal according to the first coincidence ratio; when the consistency of the first clustering grouping result is larger than or equal to a first preset threshold value, generating a target characteristic vector according to a plurality of second radio frequency pulse signals, adjusting other second radio frequency pulse signals according to the target characteristic vector, and generating a plurality of initial pulse clusters which accord with the coincidence ratio; and when the consistency of the first clustering grouping result is smaller than the first preset threshold value, adjusting the waveform characteristic and the spectrum characteristic, and re-executing the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristic and the spectrum characteristic of each second radio-frequency pulse signal.
With reference to the eighth implementation manner of the first aspect, in the ninth implementation manner of the first aspect, the method further includes: after the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio-frequency pulse signals is executed again, calculating and generating a second coincidence ratio of the second radio-frequency pulse signals; determining the consistency of the second clustering grouping results of the second radio frequency pulse signals according to the second combining ratio; and when the consistency of the second clustering grouping result is still smaller than a first preset threshold value, maintaining the initial pulse clusters generated in the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of each second radio frequency pulse signal unchanged.
According to a second aspect, an embodiment of the present invention provides a device for classifying and identifying pulse signals, including: the target sample data acquisition module is used for acquiring target sample data of the radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; the first radio frequency pulse signal generation module is used for carrying out noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; the initial pulse cluster generating module is used for clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; the target pulse cluster generating module is used for carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; the feature set extraction module is used for respectively generating a plurality of corresponding feature sets according to the target pulse clusters; and the type determining module is used for determining the type of the target pulse cluster according to the feature set.
According to a third aspect, an embodiment of the present invention provides a computer device/mobile terminal/server, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing therein computer instructions, and the processor executing the computer instructions to perform the method for classifying and identifying pulse signals according to the first aspect or any one of the embodiments of the first aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for class identification of pulse signals described in the second aspect or any one of the implementation manners of the second aspect.
The technical scheme of the invention has the following advantages:
the invention provides a classification identification method and device of pulse signals and computer equipment, wherein the method comprises the following steps: acquiring target sample data of a radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; respectively generating a plurality of corresponding feature sets according to the target pulse clusters; and determining the type of the target pulse cluster according to the feature set. The method and the device have the advantages that the detailed signal characteristic information of a time domain, a frequency domain and a space domain is determined by combining multi-dimensional high-fidelity target sample data, and the radio frequency pulse signals are identified, extracted, clustered, grouped, reasonably denoised and classified, so that the problem that the detection reliability of the existing partial discharge signal detection process is reduced is solved, the pulse type signals are effectively inhibited, the accuracy of partial discharge detection and signal source positioning is improved, and false alarms are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart illustrating a method for classifying and identifying pulse signals according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating another exemplary classification method for pulse signals according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a specific example of generating a plurality of first pulse clusters in a classification method for pulse signals according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a specific example of generating a positioning result of a plurality of first pulse clusters in a classification and identification method for pulse signals according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a distribution of pulse cluster positioning results in the pulse signal classification and identification method according to the embodiment of the present invention at a same center point;
FIG. 6 is a schematic diagram illustrating the distribution of the pulse cluster positioning results in the classification and identification method of pulse signals in the embodiment of the present invention at two central points;
FIG. 7 is a diagram illustrating the distribution of pulse cluster positioning results among a plurality of center points in the classification method for pulse signals according to the embodiment of the present invention;
FIG. 8 is a schematic diagram illustrating the unordered distribution of the pulse cluster positioning results in the classification and identification method of pulse signals according to the embodiment of the present invention;
FIG. 9 is a flowchart illustrating a specific example of determining a target pulse cluster in a classification method for pulse signals according to an embodiment of the present invention;
FIG. 10 is a flowchart illustrating an example of generating target sample data in the classification method for pulse signals according to the embodiment of the present invention;
FIG. 11 is a diagram illustrating a method for classifying and identifying pulse signals according to an embodiment of the present invention;
FIG. 12 is a diagram illustrating another exemplary method for classifying and identifying pulse signals according to the present invention;
FIG. 13 is a schematic diagram illustrating a classification method for pulse signals according to an embodiment of the present invention;
FIG. 14 is a schematic block diagram illustrating an exemplary pulse signal classification device according to an embodiment of the present invention;
FIG. 15 is a diagram showing a specific example of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements may be directly connected or indirectly connected through an intermediate medium, or may be communicated with each other inside the two elements, or may be wirelessly connected or wired connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
In the power grid equipment, various insulation protections exist, and in an area with high electric field intensity, charges move directionally at a position with weak insulation to form partial discharge without breaking down the insulation. Therefore, the detection and localization of the local signals are required for monitoring and predictive maintenance of the state of the grid equipment. In the related art, monitoring is realized mainly by manual inspection, and on-line monitoring is realized on the basis of a built-in or surface-mounted sensor for part of single equipment, so that the cost investment is high, the detection efficiency is low, and the method is not suitable for monitoring the total station of the power transformation equipment.
The partial discharge broadband radio frequency pulse detection method based on spatial coupling is suitable for carrying out full-coverage continuous online monitoring on the power transformation equipment. However, high-sensitivity coupling reception of the local broadband radio frequency pulse signal in an open space requires a broadband or ultra-wideband radio frequency sensing antenna to be configured, and various electromagnetic interference signals are easily introduced, so that false alarm and false alarm of local discharge detection are caused, unnecessary shutdown maintenance is caused, and monitoring efficiency is affected.
Specifically, in a strong electromagnetic environment of a substation, a common electromagnetic interference signal encountered by space coupling partial discharge detection through a broadband antenna may be classified into periodic narrow-band interference (e.g., radio broadcasting, mobile communication carrier, etc.), impulse-type interference (e.g., corona discharge, random pulse generated by electromagnetic switch operation or power electronics), and white noise interference according to its time-frequency characteristics. The time domain waveform characteristics of the periodic narrow-band interference signals are obviously different from those of partial discharge pulse signals, are easy to identify, and can be effectively inhibited through analog filtering or digital filtering. The pulse-type interference is difficult to identify based on simple waveform characteristics (such as width, amplitude and the like) due to the time-frequency characteristics similar to those of the partial discharge pulse signal, so that misjudgment is often caused, and the reliability of partial discharge detection is affected. At present, no mature and reliable method can achieve a relatively ideal suppression effect on pulse type interference signals of a transformer substation site. White noise covers the full frequency band of the partial discharge detection and continuously exists in the time domain, and the signal to noise ratio of the partial discharge signal can be reduced by being superposed on the partial discharge signal, so that the partial discharge signal and an impulse type interference signal are more similar in the time domain waveform, the identification difficulty of the partial discharge signal is increased, and the positioning precision of a signal source is influenced. The existing white noise suppression method, such as wavelet transform, reduces noise, and is also easy to attenuate energy and waveform of partial discharge signals due to improper parameter setting, thereby causing difficulty in subsequent partial discharge identification, positioning and diagnosis.
In addition, for a space coupling type partial discharge monitoring system for multi-sensor synchronous detection, positioning of a pulse signal source is important information for assisting pulse classification and identification. The existing vehicle-mounted space coupling partial discharge monitoring system can only carry out approximate direction angle positioning on a pulse signal source due to the fact that the distance between four sensor antennas is too close to each other, and is difficult to assist classification and identify pulses through positioning information obtained by the four sensor antennas, so that the partial discharge detection reliability is low, and the application and popularization of the system are influenced.
In summary, noise reduction and pulse interference resistance are the main problems faced by the current spatial coupling-based partial discharge broadband radio frequency pulse detection, and are the key to whether the method can be popularized and applied in the state monitoring of the power grid equipment. Because the partial discharge signal and the pulse-type interference signal have the characteristics of short time and wide frequency spectrum, the overlapping probability in the time domain is low. Based on the above, the embodiments of the present invention provide a method, an apparatus, and a computer device for classifying and identifying pulse signals, which combine with multi-dimensional signal feature information, and perform data analysis such as digital signals, machine learning, and feature mining to perform identification, extraction, clustering, grouping, reasonable noise reduction, and classification and identification on broadband radio frequency pulse signals from multiple layers, so as to achieve effective suppression on pulse-type interference signals, thereby improving accuracy of partial discharge detection and positioning.
The embodiment of the invention provides a classification and identification method of pulse signals, which comprises the following steps of:
step S11: acquiring target sample data of the radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; in this embodiment, the rf pulse signal may be a wideband or ultra-wideband rf pulse signal, and the target sample data may be a pulse signal conforming to a target frequency band range and a target signal strength range; the multiple dimensions comprise a time domain, a frequency domain and a space domain; specifically, a preset number (for example, 4) of high-precision broadband radio frequency synchronous detection sensors are distributed around the monitored power equipment, and then, the target sample data of the radio frequency pulse signal is acquired in the strong magnetic environment of the transformer substation by means of sampling, pulse detection, extraction and the like.
Step S12: performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; in this embodiment, the method of performing noise reduction processing may be digital filtering; and then, according to the main frequency band range, screening and extracting the target sample data of the radio frequency pulse signal by a digital filtering method to generate a first radio frequency pulse signal. The filtering method is not particularly limited in the present invention, for example, a wavelet denoising method may also be used, and those skilled in the art may specifically determine the filtering method according to the actual application scenario.
Because the target frequency band range set by the detection sensor in the above steps is actually far larger than the actual frequency band range of the radio frequency pulse signal, and more noise and interference are introduced into the excessively wide radio frequency signal receiving frequency band range, the noise reduction of the target sample data in the step can increase the signal-to-noise ratio of the radio frequency pulse signal, reduce the difficulty of clustering and grouping the pulse signals of different sources in the subsequent steps, and improve the efficiency of detecting the partial discharge signal.
Step S13: clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; in this embodiment, the respective obtained broadband radio frequency pulse signals are clustered and grouped according to different sensors, and then fusion clustering and grouping are performed according to the multivariate characteristic information to generate a plurality of initial pulse clusters. The first radio frequency pulse signal is sample data with multi-dimension and high fidelity, and the detailed waveform and spectrum characteristics of the broadband radio frequency pulse signal are reserved, so that clustering grouping can be performed according to different characteristic quantities and algorithms. For example, cross-correlation analysis may be performed according to full-waveform or full-spectrum sample values, so as to calculate similarity distances between different pulses, and cluster-group the similarity distances as feature quantities to obtain a plurality of initial pulse clusters.
Step S14: carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; in this embodiment, the out-of-band noise reduction and the in-band noise reduction are performed separately for each initial pulse cluster generated. And respectively carrying out noise reduction treatment on the initial pulse clusters obtained by different sensors. The processing procedure of out-of-band noise reduction may be to perform energy analysis again for each initial pulse cluster generated after clustering to determine a main frequency band range, and then remove noise outside the main frequency band range according to a digital filtering tool. And after the out-of-band denoising, performing the in-band denoising again, continuously learning each initial pulse cluster subjected to the out-of-band denoising, determining a subspace of each group of initial pulse clusters, performing the in-band denoising according to the subspace, and removing noise components which are in the same frequency range and are orthogonal to the pulse signals. The target pulse cluster can be pulse signals which come from the same physical position and are generated by the same physical effect; and calculating a pulse source positioning result according to the initial pulse cluster after the out-of-band denoising and the in-band denoising, and then performing clustering optimization according to the pulse source positioning result to generate a target pulse cluster.
Step S15: respectively generating a plurality of corresponding feature sets according to the target pulse cluster; in this embodiment, the feature set may be a pulse signal feature set, and the pulse signal feature set may include: a phase-delayed partial discharge pattern (PRPD), pulse interval time, pulse intensity, frequency spectrum, waveform, and pulse source position, where the pulse source position may be device positioning information obtained according to a signal intensity ratio and/or an arrival time difference, or may be a certain position interval located in a device body or a casing according to a difference in a propagation spectrum characteristic of a pulse signal inside the device, and the present invention is not limited thereto. Specifically, according to the generated multiple target pulse clusters, the features of each target pulse cluster are correspondingly extracted according to a preset feature set list, and a corresponding feature set is generated. Those skilled in the art can determine the pulse signal feature types included in the pulse signal feature set according to the practical application scenario, and the present invention is not limited thereto.
Step S16: and determining the type of the target pulse cluster according to the feature set. In this embodiment, the types of the target pulse cluster may include a suspected partial discharge signal, a typical pulse-type interference signal, a noise signal erroneously detected as a pulse, and an unknown signal. And classifying and identifying each target pulse cluster according to the preset partial discharge signal characteristics, the preset typical pulse signal characteristics and the generated characteristic set of each target pulse cluster.
The invention provides a classification and identification method of pulse signals, which comprises the following steps: acquiring target sample data of a radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; respectively generating a plurality of corresponding feature sets according to the target pulse clusters; and determining the type of the target pulse cluster according to the feature set. The method and the device have the advantages that the detailed signal characteristic information of a time domain, a frequency domain and a space domain is determined by combining multi-dimensional high-fidelity target sample data, and the radio frequency pulse signals are identified, extracted, clustered, grouped, reasonably denoised and classified, so that the problem that the detection reliability of the existing partial discharge signal detection process is reduced is solved, the pulse type signals are effectively inhibited, the accuracy of partial discharge detection and signal source positioning is improved, and false alarms are avoided.
As an alternative embodiment of the present invention, as shown in fig. 2, the step S14 of performing out-of-band noise reduction and in-band noise reduction processing on each initial pulse cluster to generate a plurality of target pulse clusters specifically includes:
step S141: carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters and positioning results thereof; in this embodiment, the out-of-band denoising process may be implemented by digital filtering, and the in-band denoising process may be implemented by a Principal Component Analysis (PCA) tool, according to each initial pulse cluster that has been denoised out-of-band, further remove noise components within the same frequency band range, according to each initial pulse cluster that has been denoised out-of-band and in-band, and the first pulse cluster, further according to the first pulse cluster, respectively calculate a corresponding positioning result, that is, physical position information of a signal source of each pulse signal in the first pulse cluster.
Step S142: and performing clustering optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters. In this embodiment, the pulse signals in the target pulse cluster are from the same physical location and generated by the same physical effect. The classification standard of the first pulse cluster is that the waveform characteristics and the frequency spectrum characteristics are similar, and the pulse signals with the similar waveform characteristics and the similar frequency spectrum characteristics can come from pulse signal sources at different physical positions, on one hand, the pulse signals with the similar waveform characteristics or the similar frequency spectrum characteristics can be generated by the same physical effect, similar propagation channels propagate, but the physical positions of the pulse signal sources can be different, at the moment, clustering optimization needs to be performed on each first pulse cluster again according to the positioning result of each first pulse cluster to generate a plurality of target pulse clusters; on the other hand, the plurality of first pulse clusters with dissimilar waveform characteristics or spectrum characteristics may be generated from a pulse signal source at the same physical location and through similar propagation channels, and in this case, each pulse cluster needs to be associated. For example, when a part of the pulse signal generated by the corona effect occurs at a positive peak value of the voltage and another part occurs at a negative peak value of the voltage, the plurality of first pulse clusters obtained by the steps described in the above embodiments are fused in combination with the pulse source localization result, and the target pulse clusters are generated and correlated. In this embodiment, the first pulse clusters obtained on different sensors may be cluster-optimized one by one.
As an alternative embodiment of the present invention, as shown in fig. 3, the step S141 of executing performs out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters specifically includes:
step S21: carrying out spectrum analysis on the initial pulse cluster, and determining the out-of-band noise reduction frequency band range of the initial pulse cluster; in this embodiment, the out-of-band noise reduction frequency band range may be a main frequency band range of each initial pulse cluster determined by performing energy analysis on each initial pulse cluster; and carrying out-of-band noise reduction treatment on each initial pulse cluster after clustering.
Step S22: generating a second pulse cluster according to the out-of-band noise reduction frequency band range; in this embodiment, according to the above-mentioned out-of-band noise reduction band range, the initial pulse cluster is filtered, and the noise signal and the interference signal outside the out-of-band noise reduction band range are removed by digital filtering, so as to generate the second pulse cluster.
Step S23: determining the principal dimension of the second pulse cluster according to a preset principal component analysis algorithm; in this embodiment, on one hand, unsupervised continuous learning may be performed according to a predetermined Principal Component Analysis (PCA), a pulse signal subspace of the second pulse cluster is expanded, and a Principal dimension of the second pulse cluster is determined; and supervision continuous learning can be performed according to a preset principal component analysis algorithm, the increase of pulse signal subspaces and noise component dimensions is limited, the fast convergence of the learning process is realized, and the principal dimension of each second pulse cluster is determined.
Step S24: and generating a plurality of first pulse clusters in each second pulse cluster by reducing dimensions and denoising according to the main dimensions of the second pulse clusters. In the present embodiment, a plurality of first pulse clusters are generated by removing in-band noise components other than the main dimension according to the main dimension of each second pulse cluster.
The method for classifying and identifying the pulse signals provided by the embodiment of the invention has the advantages that the main frequency band range is determined according to the energy distribution of the mixed pulse signals before clustering and grouping, and the frequency band difference exists between different grouped initial pulse cluster signals, so that the filtering and noise reduction effect is not obvious. And removing noise components which are in the same frequency range as the pulse cluster and are orthogonal to each other through in-band denoising processing. That is, by performing out-of-band denoising based on bandwidth digital filtering and in-band denoising based on machine learning on the signal of each pulse cluster after clustering, noise interference (e.g., white noise) to the pulse signal can be removed to the maximum extent. Meanwhile, the machine learning process based on the gradual convergence of the statistical pulse data ensures that the energy and waveform details of the original pulse signal (such as a partial discharge signal) are not seriously damaged.
As an optional embodiment of the present invention, as shown in fig. 4, in the step S141, the executing process of generating the positioning result of the plurality of first pulse clusters specifically includes:
step S31: respectively acquiring signal intensity ratios and/or arrival time differences of a plurality of first pulse clusters reaching each sensor; in this embodiment, the signal strength ratio of each first pulse cluster to the corresponding sensor may be the signal strength of the first pulse cluster received at the corresponding sensor end; the arrival time difference of the first pulse cluster at each sensor may be the arrival time difference between the radio frequency pulse signals (i.e., the first pulse cluster) according to each signal receiving point (e.g., sensor end). Specifically, there are three cases:
in the first case, only the signal intensity ratios of the first pulse clusters reaching the sensors are obtained; in the second case, only the arrival time difference of the first pulse cluster to each sensor is obtained; in the third case, the signal intensity ratios of the multiple first pulse clusters arriving at each sensor and the arrival time differences of the first pulse clusters arriving at each sensor are obtained.
Step S32: and generating a positioning result of the plurality of first pulse clusters according to the signal strength ratio and/or the arrival time difference. In this embodiment, the positioning result of each first pulse cluster is determined according to various parameters obtained by the method described in the above embodiment; specifically, the positioning result of the first pulse cluster may require that four sensors receive the same signal synchronously to obtain an accurate positioning result. In the actual application scenario of the substation, not all the sensors in the preset number can simultaneously detect the pulse signals sent by the preset signal source, and therefore when only the sensors less than the preset number simultaneously detect the pulse signals sent by a certain pulse source, the rough positioning result is determined, that is, the pulse signal source is positioned to a certain line or a certain direction.
Specifically, the first pulse cluster is a pulse cluster obtained based on waveform feature or spectrum feature clustering, wherein signals can be generated by the same physical effect, similar propagation channels propagate, but the physical positions of pulse signal sources are different. When determining the positioning result of the signal source of the first pulse cluster, the number of the corresponding main pulse sources may be determined according to the statistical distribution of the positioning results of all the pulse signals in the first pulse cluster. For example, as shown in fig. 5, if the signal source location results of all the pulse signals in a certain first pulse cluster are centrally distributed near a certain central point with a first probability density, the pulse signals in the first pulse cluster can be considered to be from the same pulse signal source, and the location result of the first pulse cluster is determined according to the average or statistical distribution of the location results of all the pulse signals, so that the location accuracy of the signal source can be improved.
For example, as shown in fig. 6 and 7, if the signal source location results of all the pulse signals in a certain first pulse cluster are centrally distributed around a plurality of central points with a second probability density, the pulse signals in the first pulse cluster can be considered to be from a plurality of different pulse signal sources, and at this time, the corresponding signals are selected to perform a numerical average calculation or a statistical calculation with reference to different central points, so as to determine the location result of the first pulse cluster, thereby reducing the location error for different pulse sources.
For example, as shown in fig. 8, the positioning results of the signal sources of all pulse signals in a certain first pulse cluster may also be distributed irregularly, in which case, it is not possible to simply perform numerical averaging or statistical calculation on all signals, in which case, it may be stated that an error occurs in the clustering grouping process of the first pulse cluster, and the processes of steps S11-S14 may be performed again.
Specifically, there are three cases:
in the first case, the positioning result of the first pulse cluster is determined according to the signal intensity ratio of a plurality of first pulse clusters reaching each sensor; the proportional relation between the signal intensity ratio received by each sensor and the distance of the pulse signal source can be calculated, and then the physical position of the pulse signal source is determined according to a preset trilateration method. When the pulse signal source is close to each sensor, the positioning accuracy of the positioning result obtained based on the signal intensity ratio is high, the requirements on the complexity and the cost of the sensor are low, and the method is suitable for short-distance positioning and is easily influenced by a signal attenuation model.
In the second case, the positioning result of the first pulse cluster is determined according to the arrival time difference of the plurality of first pulse clusters to each sensor; the positioning result can be obtained only according to the arrival time difference, namely the physical position of the pulse signal source is determined; the position of the pulse signal source (i.e. the position of the partial discharge source) can be determined by calculating the distance difference relation with the pulse signal source according to the arrival time difference between the radio frequency pulse signals of the signal receiving points (i.e. the sensors). Because the arrival time difference can be directly converted into the distance difference, the method is suitable for the actual application scene with higher synchronization precision of different sensor nodes, if the sensitivity and the detection distance of the partial discharge detection sensor are high enough, the partial discharge source can be accurately positioned in a wider coverage range based on a small number of distributed sensors, and the method is an effective means for carrying out equipment-level primary positioning on the partial discharge source. The transformer substation is an electromagnetic interference complex area, and any wireless interference or noise source can cause calculation errors of high-speed electromagnetic wave signal time difference, so that an effective interference suppression and denoising means is required to be provided for positioning by using the time difference method. This is why the present invention re-emphasizes denoising and interference suppression.
In the third situation, the positioning result of the first pulse cluster is determined according to the signal intensity ratio of the first pulse clusters reaching each sensor and the arrival time difference of the first pulse clusters reaching each sensor; and positioning according to the signal strength ratio and the arrival time difference of the synchronous receiving pulses of different sensors. According to the high-fidelity data, the signal intensity ratio and the arrival time difference are obtained through calculation, then the positioning hit result is obtained, the advantage complementation is realized, and the positioning precision and the positioning robustness are improved.
As an optional embodiment of the present invention, as shown in fig. 9, in step S142, performing cluster optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters, specifically including:
step S41: respectively determining the signal source positions of the first pulse clusters according to the positioning results of the first pulse clusters; in this embodiment, the signal source position of the first pulse cluster may be the signal source generating each pulse signal of the first pulse cluster, that is, the physical position of the signal source.
Step S42: when the signal source positions of the first pulse clusters are the same, the first pulse clusters are target pulse clusters; in this embodiment, when the signal sources of the pulse signals in a certain first pulse cluster are all at the same physical location, it is not necessary to cluster and group the first pulse cluster bases again, and at this time, the first pulse cluster is the target pulse cluster.
Step S43: and/or when the signal source positions of the first pulse clusters are different, generating a plurality of sub-pulse clusters according to the signal source positions, wherein the sub-pulse clusters are target pulse clusters; in this embodiment, when the signal sources of the pulse signals in a certain first pulse cluster are distributed at different physical positions, the first pulse cluster bases need to be clustered and grouped again according to the different physical positions; for example, through the step S13 described in the above embodiment, a plurality of first pulse clusters { a, B, C, D, … } are generated, where, for example, the signal source of the pulse signal in the first pulse cluster a is distributed at two positions, the first pulse cluster a needs to be re-divided according to the two positions to obtain two sub-pulse clusters a1 and a2, the pulse clusters a1 and a2 are the sub-pulse clusters of the pulse cluster a, the pulse cluster a is defined as a separable pulse cluster, and the sub-pulse clusters a1 and a2 are the smallest separable pulse cluster; at this time, the pulse target clusters are { A, A1, A2, B, C, D, … }.
Step S44: and/or when the signal source positions of different first pulse clusters are the same, generating a super pulse cluster according to the signal source positions, wherein the super pulse cluster is a target pulse cluster; in this embodiment, when the signal sources of the pulse signals in the plurality of different first pulse clusters are distributed at the same physical location, the plurality of first pulse clusters need to be merged at this time; for example, after the step S13 described in the above embodiment, a plurality of first pulse clusters { a, B, C, D, … } are generated, where, for example, the signal source of the pulse signal in the first pulse cluster C and the signal source of the pulse signal in the first pulse cluster D are distributed at the same physical location, and at this time, a super pulse cluster couter C £ D is obtained, where the pulse cluster couter C £ D is the super pulse cluster of the pulse clusters C and D, and the pulse cluster couter C $ D is defined as a separable pulse cluster, where a plurality of target pulse clusters are { a, B, C, D, couter D, … }.
Illustratively, when all pulse signals on a certain sensor generate a plurality of first pulse clusters, which are { a, B, C, D, … }, at this time, according to the first pulse clusters, the process of generating the target pulse clusters may be one or more of the above steps S42, S42, and S44, which cannot be exhaustive, but only three cases are listed.
In the first case, the signal sources of the pulse signals in the first pulse cluster a are all first physical positions, the signal sources of the pulse signals in the first pulse cluster B are all second physical positions, and the signal sources of the pulse signals in the first pulse cluster C are all third physical positions; the source of the pulse signal in the first pulse cluster D is the fourth physical location, …, at which time the target pulse clusters are { a, B, C, D, … }.
In a second case, the signal sources of the pulse signals in the first pulse cluster a are the first physical position and the second physical position, the signal sources of the pulse signals in the first pulse cluster B are the third physical position and the fourth physical position, and the signal sources of the pulse signals in the first pulse cluster C are the fourth physical position and the fifth physical position; the signal source of the pulse signal in the first pulse cluster D is the sixth physical position and the seventh physical position, …, and at this time, the target pulse clusters are { a, a1, a2, B1, B2, C1, C2, D1, D2, … }.
In a third case, the signal source of the pulse signal in the first pulse cluster a is the first physical location, the signal source of the pulse signal in the first pulse cluster B is the first physical location, the signal source of the pulse signal in the first pulse cluster C is the first physical location, and the signal sources of the pulse signals in the first pulse cluster D are all the first physical locations, …, at this time, the plurality of target pulse clusters are { a, B, C, D, …, a £ B £ C $ D $ … }.
Further, the positioning result of the pulse signal source may be used to verify the plurality of first pulse clusters obtained in step S13. By locating the pulse signal included in each first pulse cluster obtained in step S13, if the clustering result is reasonable, the location result with a certain distribution rule can be obtained under normal conditions, for example, the location result is regularly distributed around a certain point or a plurality of points, specifically referring to fig. 5, 6, and 7. On the contrary, if the positioning results of the signals contained in the same grouped pulse cluster are distributed irregularly, referring to fig. 8, this situation may correspond to a plurality of reasons: (1) possibly caused by unreasonable clustering grouping in the step S13, the step S13 can be repeated to iteratively optimize pulse clustering grouping until the verification is passed; (2) it is possible that the pulse cluster is a noisy signal that is falsely detected as a pulse, which can be identified in combination with other characteristics of the pulse cluster to remove the noise component.
Further, if the positioning results of the signal sources included in the same pulse cluster are distributed around a plurality of center points, as shown in fig. 7, it is likely that the similarity distance threshold for clustering the groups in step S13 is selected too large, resulting in a group with insufficient fineness. For example, it may be set that the positioning results are distributed over three central points, i.e. the clustering is considered to be not fine enough. At this time, the step S13 may be repeated to iteratively optimize the cluster grouping, and the cluster optimization result using the positioning location information in this step is mutually verified until the signal source distribution location is near the two central points.
As an optional implementation manner of the present invention, as shown in fig. 10, in the step S11, the step of acquiring target sample data of the radio frequency pulse signal specifically includes:
step S111: acquiring a simulated radio frequency signal which accords with a target frequency band range and a target signal intensity range; in this embodiment, the target frequency band range may be an partial discharge detection frequency band determined by monitoring a specific situation of a site through adjustable filtering, and the target frequency band range and the target signal intensity range may be determined according to a practical situation of the site of partial discharge detection, for example, types of monitored power equipment and main insulation faults thereof, a sensor deployment manner, a distance from a potential partial discharge signal source, a frequency band range of a peripheral main electromagnetic interference signal, and the like, and by the above setting, a frequency band in which a main narrowband interference signal is located, for example, an 88-108 MHz frequency band in which radio frequency modulation broadcast interference is located, a VHF frequency band 48.5-223 MHz in which radio television broadcast interference is located, UHF frequency bands 470-566 MHz and 606-798 MHz in which radio mobile phone communication interference is located, and the like, can be excluded. The target frequency band range can be determined according to the signal strength and frequency of the narrow-band interference and the pulse signal energy distribution of the frequency band, that is, it is determined to apply filtering in a certain frequency band or several frequency bands to remove the narrow-band interference. The method can inhibit the narrow-band interference, simultaneously can not cause loss to the energy and the waveform of the pulse signal, and is convenient for the subsequent classification and identification of the broadband radio frequency pulse signal.
Because the specific frequency band range of the radio-frequency pulse signal received through spatial coupling is influenced by the factors, the target frequency band range set on site is difficult to be accurate to the actual requirement, and a conservative configuration is often adopted. The target frequency band range is generally much larger than the frequency band range of the actually received rf pulse signal.
Step S112: acquiring the highest frequency of the analog radio frequency signal, and determining the sampling frequency according to the highest frequency; in this embodiment, the sampling rate of the analog rf signal may be more than two times, preferably three times or more than the highest frequency of the analog rf signal.
Step S113: sampling the analog radio frequency signal according to the sampling frequency, the sampling vertical resolution and the sampling clock synchronization precision to generate sample data of the radio frequency signal; in the embodiment, the sampling vertical resolution is related to the dynamic detection range of the pulse signal, and the delay error of the subsequent pulse signal detection and extraction is determined according to the sampling vertical resolution and the sampling rate; the time difference of the pulse signals reaching each sensor is calculated and determined according to the synchronous precision of the sampling clocks of different sensors, and generally less than 1 nanosecond is needed. The positioning accuracy based on the arrival time difference of the multi-sensor pulse signals is influenced according to the sampling rate, the vertical resolution and the sampling clock synchronization accuracy of different sensors. The selection of the specific sampling rate, vertical resolution and sampling clock synchronization accuracy depends on the field situation, and is not limited herein.
Specifically, the high-precision digital sampling may be implemented by a single high-speed ADC chip, or may be implemented by performing time-interleaved sampling based on a plurality of low-speed ADC chips, which is not limited herein. The sampling synchronization among different sensors can be realized by sharing a certain sampling clock source on the same mainboard, and can also be realized by keeping synchronization with a certain external reference clock source through a coaxial cable, an optical fiber, a GPS or a wireless beacon and the like, and no special limitation is made here.
Specifically, continuous high-precision digital sampling of the analog radio-frequency signal by the single sensor can ensure that detailed time-domain and frequency-domain characteristic information contained in the original analog radio-frequency signal, including waveform and spectrum characteristics and occurrence rules and evolution of the radio-frequency signal in the time domain, can be highly restored from the obtained sample data. The position information of the radio frequency signal source can be supplemented from the dimension of the space domain by continuously and synchronously sampling the same analog radio frequency signal through a plurality of high-precision sensors which are distributed and deployed. The high-resolution sample data obtained by the step can provide detailed characteristic information of the radio frequency signal from three dimensions of a time domain, a frequency domain and a space domain, and is the basis and the premise of subsequent signal processing and data analysis.
Step S114: and extracting sample data which accords with the characteristics of the preset pulse signal from the sample data of the radio frequency signal, and generating target sample data of the radio frequency pulse signal. Specifically, the high-resolution sample data obtained in the previous step includes all the pulse-type and non-pulse-type radio frequency signals, and therefore, according to the sample data of the acquired radio frequency signals, sample data with a waveform conforming to the characteristics of the pulse signals is extracted. The detection of the pulse signal can improve the detection capability of the weak pulse signal by presetting a noise reduction algorithm, and the whole segment of original sample data containing the pulse signal can be extracted and stored after the position of the pulse signal is detected. In addition, the detection and extraction of the pulse signals can be independently performed on different sensors, and the pulse detection and extraction which are mutually related can also be performed after a plurality of sensors are synchronously triggered.
In this embodiment, the extraction of sample data conforming to the pulse signal characteristics may be achieved through various algorithms, specifically, in the embodiment of the present invention, the bottom noise and the energy mutation of the radio frequency signal may be compared and detected through a moving window (for example, an averaging window), or the matching detection may be performed through a predetermined waveform characteristic set or a specific pulse characteristic set, and a specific algorithm is not limited herein.
As an optional implementation manner of the present invention, the performing noise reduction processing on target sample data of the radio frequency pulse signal to generate the first radio frequency pulse signal specifically includes: performing spectrum analysis on target sample data to determine a frequency band range of the target sample data; and generating a first radio frequency pulse signal according to the frequency band range and the target sample data. In this embodiment, it can be realized by digital filtering, and the main frequency band range of the pulse signal can be determined according to the energy distribution. Specifically, the pulse signal energy may be represented by a 95 percentile, i.e., at least 95% of the pulse signal energy is contained in the determined frequency band; local signal-to-noise ratio maximization approximation criteria can also be used within a certain pulse energy percentile range, for example, within a 90% -100% pulse energy range, a certain target frequency band range is selected to achieve signal-to-noise ratio maximization. In practical applications, the pulse signal energy range and the optimal filtering frequency band should be selected according to specific situations, and are not limited specifically herein.
In the present invention, if there are narrowband interference signals with stronger energy near one or some frequency bands with higher pulse energy density, it should be determined according to the specific situation, for example, if the influence on the clustering result in step S13 is limited, the filtering removal may not be performed in this step, and the subsequent steps after clustering grouping are left for removal; on the contrary, if the effect of clustering grouping in the step S13 is seriously affected by the superposition of these narrowband interferences on the pulse signal, the narrowband interferences can be partially or completely removed in this step, and at this time, the narrowband interferences can be backed up and retained.
As an optional implementation manner of the present invention, the step of clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters specifically includes: firstly, dividing a first radio frequency pulse signal into a plurality of second radio frequency pulse signals according to sensor identification information of the first radio frequency pulse signal; and secondly, respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio frequency pulse signals. In this embodiment, the first rf pulse information is divided into rf pulse signals received by different sensor devices based on the failure of the receiving sensor. And then dividing each second radio frequency pulse signal into a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio frequency pulse signals. The features may be full waveform or full spectrum sample values, which are then clustered. According to specific situations, the similarity distance between different pulses can be calculated by selecting the sample values of only a part of intercepted waveforms or frequency bands as features. For example, in order to reduce the computational resource overhead of clustering, improve the clustering efficiency, and the like, on the premise that clustering has a better evaluation result, only some characteristic values (such as maximum amplitude, width, rise time, fall time, and the like) of waveforms can be selected to measure the similarity distance between different pulses, and then each second radio frequency pulse signal is clustered and grouped according to the characteristic of the similarity distance to generate a plurality of initial pulse clusters.
As an optional implementation manner of the present invention, the method for classifying and identifying a pulse signal further includes:
on the basis of respectively clustering and grouping the broadband radio frequency pulse signals (namely the first radio frequency pulse signals) acquired by each sensor, fusion clustering and grouping and mutual verification can be performed by using multivariate characteristic information vectors provided by synchronous sampling of a plurality of sensors. Due to different signal propagation channels and distances from pulse signal sources, waveforms and spectrum characteristics of the same pulse signal received by different sensors are inconsistent, and therefore different results may be obtained by grouping pulse clusters independently on different sensors. Before multi-sensor fusion clustering grouping, the consistency degree of clustering grouping results on different sensors is fully evaluated. For sensors with poor consistency of clustering results and results of most other sensors, multi-sensor fusion clustering groups should not be included, so as to avoid adverse effects on fusion clustering effects. The evaluation procedure was as follows:
firstly, calculating and generating a first coincidence ratio of each second radio frequency pulse signal according to a plurality of initial pulse clusters corresponding to the second radio frequency pulse signals; in the present embodiment, it is assumed that all pulses in the corresponding second rf pulse signal are divided into 4 initial pulse clusters, labeled as { a1, B1, C1, D1} and { a2, B2, C2, D2} on two sensors for synchronous detection. The first coincidence ratio, namely, the coincidence ratios of A1 n A2, B1 n B2, C1 n C2, D1 n D2 are calculated from the pulse time stamps.
Secondly, determining the consistency of the first clustering grouping results of the second radio frequency pulse signals according to the first coincidence ratio; in this embodiment, the consistency of the first clustering result is determined according to the first overlapping ratio, and when the first overlapping ratio is higher than or equal to the threshold value, the consistency is better, and at this time, the consistency of the first clustering result is greater than or equal to the first preset threshold value. When the first coincidence ratio is lower than the threshold value, the consistency is poor, and the consistency of the first clustering grouping result is smaller than a first preset threshold value.
Specifically, assume that on two synchronously-detected sensors, all pulses in the corresponding second RF pulse signal are divided into 4 initial pulse clusters, labeled { A1, B1, C1, D1} and { A2, B2, C2, D2}, respectively. If the first coincidence ratios of A1 & n A2, B1 & n B2, C1 & n C2, D1 & n D2 calculated from the pulse timestamps are all above 80%, the cluster grouping results of the two sensors can be considered to be better consistent. It should be noted that this is only an example of the implementation of the present invention, and the definition of the consistency of the clustering results of different sensors is not limited herein.
On one hand, when the consistency of the first clustering grouping result is greater than or equal to a first preset threshold value, generating a target characteristic vector according to a plurality of second radio frequency pulse signals, adjusting other second radio frequency pulse signals according to the target characteristic vector, and generating a plurality of initial pulse clusters which accord with the coincidence ratio; in this embodiment, when there are N sensors, N second rf pulse signals are correspondingly provided, and when the consistency of the clustering grouping results of the N sensors is greater than or equal to the first preset threshold, which indicates that the consistency is high, basic clustering features (e.g., waveforms) may be combined into an N-ary target feature vector according to the number of the sensors to perform fused clustering grouping, and the clustering grouping results on other individual sensors are corrected according to the target feature vector.
On the other hand, when the consistency of the first clustering grouping result is smaller than the first preset threshold, the waveform characteristic and the spectrum characteristic are adjusted, and the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristic and the spectrum characteristic of each second radio-frequency pulse signal is executed again. In this embodiment, when there are N sensors, N second rf pulse signals are correspondingly provided, and when the consistency of the clustering result of the N sensors is smaller than a first preset threshold, it indicates that the consistency is poor, that is, the clustering result (i.e., the generated initial pulse clusters) of M sensors in the N sensors is lower than the consistency of other sensors, and at this time, the waveform characteristic and the spectrum characteristic need to be adjusted, so as to re-cluster the second rf pulse signals of the M sensors. Namely, the step of generating a plurality of initial pulse clusters respectively according to the waveform characteristics and the spectrum characteristics of each second radio frequency pulse signal is executed again.
As an optional implementation manner of the present invention, the method for classifying and identifying a pulse signal further includes:
firstly, after the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of each second radio-frequency pulse signal is executed again, calculating a second coincidence ratio of each second radio-frequency pulse signal; determining the consistency of the second clustering grouping results of the second radio frequency pulse signals according to the second combining ratio; and when the consistency of the second clustering grouping result is still smaller than the first preset threshold value, maintaining the initial pulse clusters generated in the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of each second radio frequency pulse signal. In this embodiment, after the step of generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of each second radio frequency pulse signal is executed again by the method described in the above embodiment, if there still exists that M sensors cannot achieve higher consistency with the clustering results of other N-M sensors, the respective clustering grouping results on the M sensors are maintained, and only the characteristics of the N-M sensors with higher consistency of the clustering results form an N-M-ary target feature vector for performing fused clustering grouping. Specifically, the grouping result obtained by the fusion clustering can be used as a basis for re-clustering the M sensors with poor consistency of the clustering result, and specifically, a decision is needed according to the M/N ratio, and the decision can be removed or re-clustered. If the consistency of the grouping results of the M sensors is still poor after the clustering parameter iterative adjustment, the clustering grouping results of the original sensors are kept, and multi-sensor fusion clustering can be omitted.
It should be noted that, in this embodiment, all measures in different cases are not listed in detail, but a few typical cases are listed, so as to illustrate the promoting effect of the multivariate feature information vector provided by the multi-sensor synchronous sampling on improving the effectiveness and robustness of clustering grouping. The specific definition of the consistency of the clustering results of different sensors and the specific measures to be taken under different conditions are not limited herein.
In particular, the amplitude proportion and the time difference of the same pulse signal received by a plurality of sensors can also be used as characteristic information of cluster grouping. According to specific situations, if the evaluation of clustering grouping results obtained based on waveform or spectrum characteristic information alone is poor, the clustering grouping can be optimized by combining the amplitude ratio and the time difference in the step; on the contrary, if the clustering grouping obtained based on the waveform or spectrum characteristic information alone has a better evaluation result, the clustering grouping can be selected to be reused in the subsequent steps so as to perform optimization and external check on the clustering grouping result. Generally, the smaller the similarity distance between signal samples of the same pulse cluster, the larger the similarity distance between signal samples of different pulse clusters, and the better the evaluation result of clustering grouping. In the present invention, the results can be evaluated using various internal indexes of clustering performance, such as DB index, Dunn index, etc., without being limited thereto.
In the invention, when the broadband radio frequency pulse signals are clustered and grouped, according to the specifically selected clustering characteristics, various distance functions can be used for measuring the similarity between different pulse signals, such as Euclidean distance, Manhattan distance, cosine distance and the like, and no special limitation is made herein; when different classes of pulse packets are combined, different distance calculation methods, such as the shortest distance method, the longest distance method, the intermediate distance method, the center of gravity method, the class averaging method, and the like, may be used, and are not limited herein.
The choice of pulse clustering algorithm in the implementation and application is also dependent on the clustering characteristics used, the amount of data, and the requirements on computational resources and efficiency. Without loss of generality, different Hierarchical (Hierarchical) clustering algorithms, Partitional (partial) clustering algorithms, and other traditional or newly developed clustering algorithms may be used, without special limitation.
Firstly, a sensor array composed of a broadband antenna and a simulation conditioning unit performs spatial coupling reception on a radio frequency electromagnetic signal, then, output radio frequency analog signals are subjected to high-precision synchronous sampling in a data acquisition unit, then, real-time pulse detection and extraction are performed through firmware operated on a logic circuit of the data acquisition unit, finally, obtained multi-dimensional high-fidelity sample data are transmitted to a data analysis unit through a wired or wireless communication mode and are used as input of a pulse classification identification software module, namely, classification identification of pulse signals is performed, and detection and extraction of the pulse signals can also be realized on a special or general computer such as an industrial personal computer, an edge server or a remote server.
The method for classifying and identifying the pulse signals provided by the embodiment of the invention is described in detail with reference to fig. 12, and includes the steps of firstly, carrying out space coupling reception on radio frequency electromagnetic signals by a sensor array composed of a broadband antenna and a simulation conditioning unit, then carrying out high-precision synchronous sampling on the radio frequency analog signals by a data acquisition unit, then directly transmitting sample data to a data analysis unit based on a special or general processor in a wired or wireless communication mode, and then carrying out pulse detection and extraction in a software mode. This embodiment has no strict time delay and resource limitations on the pulse detection and extraction algorithm, allowing various signal processing approaches to be applied to optimize the detection of weak pulse signals. However, due to the software implementation, the calculation efficiency is slow and the requirement on the data transmission bandwidth between the data acquisition unit and the data analysis unit is high. In the specific implementation and application of the present invention, the two embodiments can be complementarily combined to obtain better pulse sample data acquisition effect.
For the sample data of the radio frequency signals from multiple sensors, independently triggered pulse detection and extraction can be performed based on the respective data of each sensor, and in this case, the method described in fig. 11 and the method shown in fig. 12 can be used in combination to achieve synchronously triggered pulse detection and extraction. The latter can better ensure that signal data from all sensors are obtained at the same time stamp, provide a better data base for subsequent analysis, but the synchronous trigger pulse detection can also extract data irrelevant to the pulse signal, and increase the data volume and the communication bandwidth. In the specific implementation, the configuration needs to be selected according to the field situation and the system mode, and no special limitation is made here.
In the embodiment, noise reduction is performed before grouping broadband radio frequency pulse signal sample data to improve a signal-to-noise ratio, different pulse cluster groups { a, B, …, M } are obtained through clustering grouping, similar noise reduction and pulse signal source positioning are performed on each pulse cluster group, clustering optimization and verification are performed on previous pulse clusters based on a positioning result to obtain new pulse cluster groups { a ', B', …, N }, and finally feature mining extraction is performed on each pulse cluster group, and pulse classification and identification are performed according to a feature set and partial discharge diagnosis field knowledge of each pulse cluster group.
An embodiment of the present invention provides a classification and identification apparatus for pulse signals, as shown in fig. 14, including:
a target sample data obtaining module 51, configured to obtain target sample data of the radio frequency pulse signal, where the target sample data is multidimensional high-fidelity sample data; the detailed implementation can be referred to the related description of step S11 in the above method embodiment.
The first radio frequency pulse signal generating module 52 is configured to perform noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; the detailed implementation can be referred to the related description of step S12 in the above method embodiment.
An initial pulse cluster generating module 53, configured to perform cluster grouping on the first radio frequency pulse signals to generate a plurality of initial pulse clusters; the detailed implementation can be referred to the related description of step S13 in the above method embodiment.
A target pulse cluster generating module 54, configured to perform out-of-band noise reduction and in-band noise reduction on each initial pulse cluster, and generate a plurality of target pulse clusters; the detailed implementation can be referred to the related description of step S14 in the above method embodiment.
A feature set extraction module 55, configured to generate a plurality of corresponding feature sets according to the target pulse clusters; the detailed implementation can be referred to the related description of step S15 in the above method embodiment.
And a type determining module 56 for determining the type of the target pulse cluster according to the feature set. The detailed implementation can be referred to the related description of step S16 in the above method embodiment.
The invention provides a classification and identification device of pulse signals, which comprises: the target sample data acquisition module is used for acquiring target sample data of the radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data; the first radio frequency pulse signal generation module is used for carrying out noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal; the initial pulse cluster generating module is used for clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters; the target pulse cluster generating module is used for carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters; the feature set extraction module is used for respectively generating a plurality of corresponding feature sets according to the target pulse clusters; and the type determining module is used for determining the type of the target pulse cluster according to the feature set. The method has the advantages that the detailed signal characteristic information of a time domain, a frequency domain and a space domain is determined by combining multi-dimensional high-fidelity target sample data, the radio frequency pulse signals are identified, extracted, clustered, grouped, reasonably denoised and classified, the problem that the detection reliability of the existing partial discharge signal detection process is reduced is solved, the signal to noise ratio of the partial discharge signal detection process can be obviously improved on the premise of not damaging the waveform characteristics of the pulse signals, the pulse type signals are effectively inhibited, the accuracy of partial discharge detection and signal source positioning is improved, false alarms and false alarms are avoided, the maintenance cost of power grid equipment is reduced, the stable and safe operation of a power grid is guaranteed, and the requirement of safe, reliable and comprehensive partial discharge detection is met.
An embodiment of the present invention further provides a computer device, as shown in fig. 15, the computer device may include a processor 61 and a memory 62, where the processor 61 and the memory 62 may be connected by a bus 60 or in another manner, and fig. 8 takes the example of connection by the bus 60 as an example.
The processor 61 may be a Central Processing Unit (CPU). The Processor 61 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 62 is a non-transitory computer readable storage medium, and can be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the classification and identification method of pulse signals in the embodiment of the present invention. The processor 61 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 62, that is, implements the classification and identification method of the pulse signal in the above method embodiment.
The memory 62 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by the processor 61, and the like. Further, the memory 62 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 62 may optionally include memory located remotely from the processor 61, and these remote memories may be connected to the processor 61 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 62, and when executed by the processor 61, perform a classification and identification method of the pulse signal as in the embodiment shown in fig. 1 to 10.
The specific details of the computer device may be understood by referring to the corresponding related descriptions and effects in the embodiments shown in the above figures, which are not described herein again.
The embodiment of the present invention further provides a non-transitory computer readable medium, where the non-transitory computer readable storage medium stores a computer instruction, and the computer instruction is used to enable a computer to execute the method for classifying and identifying a pulse signal described in any one of the above embodiments, where the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), a Solid-State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (13)
1. A classification and identification method of pulse signals is characterized by comprising the following steps:
acquiring target sample data of a radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data;
performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal;
clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters;
carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters;
respectively generating a plurality of corresponding feature sets according to the target pulse clusters;
and determining the type of the target pulse cluster according to the feature set.
2. The method according to claim 1, wherein the step of performing out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters specifically comprises:
carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters and positioning results thereof;
and performing cluster optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters.
3. The method according to claim 2, wherein the step of performing out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of first pulse clusters specifically comprises:
performing spectrum analysis on the initial pulse cluster to determine an out-of-band noise reduction frequency band range of the initial pulse cluster;
generating a second pulse cluster according to the out-of-band noise reduction frequency band range;
determining the principal dimension of the second pulse cluster according to a preset principal component analysis algorithm;
and generating a plurality of first pulse clusters in each second pulse cluster by reducing dimensions and denoising according to the main dimensions of the second pulse clusters.
4. The method according to claim 3, wherein the step of generating the localization result of the plurality of first pulse clusters comprises:
respectively acquiring signal intensity ratios and/or arrival time differences of a plurality of first pulse clusters reaching each sensor;
and generating a positioning result of a plurality of first pulse clusters according to the signal strength ratio and/or the arrival time difference.
5. The method according to claim 4, wherein the performing cluster optimization on the first pulse cluster according to the positioning result to generate a plurality of target pulse clusters specifically comprises:
respectively determining the signal source positions of the first pulse clusters according to the positioning results of the first pulse clusters;
when the signal source positions of the first pulse clusters are the same, the first pulse clusters are target pulse clusters;
and/or when the signal source positions of the first pulse clusters are different, generating a plurality of sub-pulse clusters according to the signal source positions, wherein the sub-pulse clusters are target pulse clusters;
and/or when the signal source positions of different first pulse clusters are the same, generating a super pulse cluster according to the signal source positions, wherein the super pulse cluster is a target pulse cluster.
6. The method according to claim 1, wherein the step of acquiring target sample data of the rf pulse signal specifically comprises:
acquiring a simulated radio frequency signal which accords with a target frequency band range and a target signal intensity range;
acquiring the highest frequency of the analog radio frequency signal, and determining a sampling frequency according to the highest frequency;
sampling the analog radio frequency signal according to the sampling frequency, the sampling vertical resolution and the sampling clock synchronization precision to generate sample data of the radio frequency signal;
and extracting sample data which accords with the characteristics of a preset pulse signal from the sample data of the radio frequency signal, and generating target sample data of the radio frequency pulse signal.
7. The method according to claim 1, wherein the performing noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal specifically includes:
performing spectrum analysis on the target sample data to determine a frequency band range of the target sample data;
and generating a first radio frequency pulse signal according to the frequency band range and the target sample data.
8. The method according to claim 1, wherein the clustering the first rf pulse signals into groups to generate a plurality of initial pulse clusters comprises:
dividing the first radio frequency pulse signal into a plurality of second radio frequency pulse signals according to the sensor identification information of the first radio frequency pulse signal;
and respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio frequency pulse signals.
9. The method of claim 8, further comprising:
calculating and generating a first coincidence ratio of each second radio-frequency pulse signal according to a plurality of initial pulse clusters corresponding to the second radio-frequency pulse signals;
determining a first clustering grouping result of each second radio frequency pulse signal according to the first coincidence ratio;
when the consistency of the first clustering grouping result is larger than or equal to a first preset threshold value, generating a target characteristic vector according to a plurality of second radio frequency pulse signals, adjusting other second radio frequency pulse signals according to the target characteristic vector, and generating a plurality of initial pulse clusters which accord with the coincidence ratio;
and when the consistency of the first clustering grouping result is smaller than the first preset threshold value, adjusting the waveform characteristic and the spectrum characteristic, and re-executing the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristic and the spectrum characteristic of each second radio-frequency pulse signal.
10. The method of claim 9, further comprising:
after the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of the second radio-frequency pulse signals is executed again, calculating and generating a second coincidence ratio of the second radio-frequency pulse signals;
determining the consistency of the second clustering grouping results of the second radio frequency pulse signals according to the second combining ratio;
and when the consistency of the second clustering grouping result is still smaller than a first preset threshold value, maintaining the initial pulse clusters generated in the step of respectively generating a plurality of initial pulse clusters according to the waveform characteristics and the spectrum characteristics of each second radio frequency pulse signal unchanged.
11. A device for classifying and identifying pulse signals is characterized by comprising:
the target sample data acquisition module is used for acquiring target sample data of the radio frequency pulse signal, wherein the target sample data is multi-dimensional high-fidelity sample data;
the first radio frequency pulse signal generation module is used for carrying out noise reduction processing on target sample data of the radio frequency pulse signal to generate a first radio frequency pulse signal;
the initial pulse cluster generating module is used for clustering and grouping the first radio frequency pulse signals to generate a plurality of initial pulse clusters;
the target pulse cluster generating module is used for carrying out-of-band noise reduction and in-band noise reduction on each initial pulse cluster to generate a plurality of target pulse clusters;
the feature set extraction module is used for respectively generating a plurality of corresponding feature sets according to the target pulse clusters;
and the type determining module is used for determining the type of the target pulse cluster according to the feature set.
12. A computer device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the one processor to cause the at least one processor to perform the steps of the method for class recognition of pulse signals according to any one of claims 1 to 10.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for classification recognition of pulse signals according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193883.4A CN112307969B (en) | 2020-10-30 | 2020-10-30 | Pulse signal classification identification method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011193883.4A CN112307969B (en) | 2020-10-30 | 2020-10-30 | Pulse signal classification identification method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112307969A true CN112307969A (en) | 2021-02-02 |
| CN112307969B CN112307969B (en) | 2024-03-12 |
Family
ID=74333068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011193883.4A Active CN112307969B (en) | 2020-10-30 | 2020-10-30 | Pulse signal classification identification method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112307969B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240057A (en) * | 2021-07-12 | 2021-08-10 | 武汉中原电子信息有限公司 | High-precision error detection method and system based on electric power data acquisition |
| CN113361435A (en) * | 2021-06-16 | 2021-09-07 | 中国农业大学 | Signal curve automatic deconvolution method realized by convolutional neural network |
| CN113721219A (en) * | 2021-10-08 | 2021-11-30 | 中国电子科技集团公司第三十八研究所 | Radar signal sorting method and system based on multi-parameter clustering |
| CN115603800A (en) * | 2022-12-14 | 2023-01-13 | 成都川美新技术股份有限公司（Cn） | Method for discovering and identifying weak satellite signals based on multi-dimensional features |
| CN117155746A (en) * | 2023-10-31 | 2023-12-01 | 中孚安全技术有限公司 | Electromagnetic signal combination processing method, system and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7397415B1 (en) * | 2006-02-02 | 2008-07-08 | Itt Manufacturing Enterprises, Inc. | System and method for detecting and de-interleaving radar emitters |
| WO2016019666A1 (en) * | 2014-08-07 | 2016-02-11 | 国家电网公司 | Method and device for detecting partial discharge of cable |
| CN107942210A (en) * | 2017-11-14 | 2018-04-20 | 国网上海市电力公司 | The classification of transformer pulse electric current Partial Discharge and denoising method and system |
| CN109901031A (en) * | 2019-02-27 | 2019-06-18 | 西安电子科技大学 | Signal De-noising Method, information data processing terminal for local discharge signal |
-
2020
- 2020-10-30 CN CN202011193883.4A patent/CN112307969B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7397415B1 (en) * | 2006-02-02 | 2008-07-08 | Itt Manufacturing Enterprises, Inc. | System and method for detecting and de-interleaving radar emitters |
| WO2016019666A1 (en) * | 2014-08-07 | 2016-02-11 | 国家电网公司 | Method and device for detecting partial discharge of cable |
| CN107942210A (en) * | 2017-11-14 | 2018-04-20 | 国网上海市电力公司 | The classification of transformer pulse electric current Partial Discharge and denoising method and system |
| CN109901031A (en) * | 2019-02-27 | 2019-06-18 | 西安电子科技大学 | Signal De-noising Method, information data processing terminal for local discharge signal |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361435A (en) * | 2021-06-16 | 2021-09-07 | 中国农业大学 | Signal curve automatic deconvolution method realized by convolutional neural network |
| CN113240057A (en) * | 2021-07-12 | 2021-08-10 | 武汉中原电子信息有限公司 | High-precision error detection method and system based on electric power data acquisition |
| CN113721219A (en) * | 2021-10-08 | 2021-11-30 | 中国电子科技集团公司第三十八研究所 | Radar signal sorting method and system based on multi-parameter clustering |
| CN115603800A (en) * | 2022-12-14 | 2023-01-13 | 成都川美新技术股份有限公司（Cn） | Method for discovering and identifying weak satellite signals based on multi-dimensional features |
| CN117155746A (en) * | 2023-10-31 | 2023-12-01 | 中孚安全技术有限公司 | Electromagnetic signal combination processing method, system and medium |
| CN117155746B (en) * | 2023-10-31 | 2024-02-23 | 中孚安全技术有限公司 | Electromagnetic signal combination processing method, system and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112307969B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112307969B (en) | Pulse signal classification identification method and device and computer equipment | |
| CN108469560B (en) | Electromagnetic interference objective complexity evaluation method based on rapid S-transform time-frequency space model | |
| Iorkyase et al. | Improving RF-based partial discharge localization via machine learning ensemble method | |
| CN103267932B (en) | A kind of GIS partial discharge detection system and method | |
| CN103197218B (en) | A kind of high-voltage cable insulation defect partial discharge electrification detection diagnostic method | |
| CN109799434A (en) | PD Pattern Recognition system and method | |
| CN107729916B (en) | ISODATA-based interference source classification and identification algorithm | |
| CN102510363A (en) | LFM (linear frequency modulation) signal detecting method under strong interference source environment | |
| CN102298685B (en) | Automotive electronic radio-frequency identification parameter detecting system based on virtual instrument | |
| CN103941254A (en) | Soil physical property classification recognition method and device based on geological radar | |
| CN110427878B (en) | Method and system for identifying rapid radio storm signals | |
| CN104869630A (en) | Pseudo base station rapid positioning method and system based on offline fingerprint database | |
| CN108337645B (en) | Gridding radio signal monitoring system architecture and interference signal joint detection method | |
| Mishra et al. | Self-organizing feature map based unsupervised technique for detection of partial discharge sources inside electrical substations | |
| CN111175614A (en) | Partial discharge acquisition and positioning method, device and system | |
| CN115993511A (en) | Partial discharge type high-precision detection and identification device, method and equipment | |
| Bui et al. | A performance study of earth networks total lighting network (ENTLN) and worldwide lightning location network (WWLLN) | |
| CN216848010U (en) | Cable partial discharge online monitoring device for edge calculation | |
| Yang et al. | Partial discharge signal extraction method based on EDSSV and low rank RBF neural network | |
| Hamid et al. | Spectrum sensing through spectrum discriminator and maximum minimum eigenvalue detector: A comparative study | |
| CN112881812A (en) | Full-flash real-time positioning method and device based on machine learning coding | |
| CN108196269A (en) | The weak harmonic interference signals detection method of anti-interference antenna of satellite navigation internal system | |
| Miao et al. | Application of one-class classification in NLOS identification of UWB positioning | |
| CN117031509A (en) | Soil humidity inversion method and device integrating isolated forest and deep learning | |
| CN112964938B (en) | Lightning single-station positioning method, device and system based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |